Danelle is CMO at Blue Hexagon. She has more than 15 years of experience bringing new technologies to market. Prior to Blue Hexagon, Danelle was VP Marketing at SafeBreach where she built the marketing team and defined the Breach and Attack Simulation category. Previously, she led strategy and marketing at Adallom, a cloud security company acquired by Microsoft. She was also Director, Security Solutions at Palo Alto Networks, driving growth in critical IT initiatives like virtualization, network segmentation and mobility.

As the capabilities and pervasiveness of machine learning (ML) and artificial intelligence (AI) increasingly affect society, there is increasing concern about the safety of such systems, i.e. the potential of accidental harm from implementation errors and unintended consequences in ML algorithms. As a result, there has been increasing interest in the nascent field of AI safety [1, 2, 3, 4, 5, 6], which seeks to understand and solve the technical challenges in developing and deploying AI that does what it is intended to do. The purpose of this chapter is to explore how the study of AI safety intersects with that of evolutionary computation (EC), to both highlight an exciting and important set of safety problems within EC, and to suggest that evolution and EC have important insights that could benefit the general study of AI safety. To frame the problem of AI safety, we adopt the framework of Amodei et al. [1], which defines AI safety as concerned with accidents in ML systems, and defines five problems within three broad categories of issues: (1) specifying the wrong objective function, (2) making safe and efficient use of a true but expensive objective (e.g.

Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge integration as well as higher-level reasoning capabilities with the methods still pose a hindrance. In this work, we present a brief survey of a few representative reasoning mechanisms, knowledge integration methods and their corresponding image understanding Figure 1: The diagram shows the information hierarchy for applications developed by various groups images and the knowledge associated with each level of information. of researchers, approaching the problem from a variety of angles. Furthermore, we discuss upon key efforts on integrating external knowledge with neural paper is to present a survey of recent works (including a few networks. Taking cues from these efforts, we of our works) in image understanding where knowledge and conclude by discussing potential pathways to improve reasoning plays an important role.

Automatic program correction is an active topic of research, which holds the potential of dramatically improving productivity of programmers during the software development process and correctness of software in general. Recent advances in machine learning, deep learning and NLP have rekindled the hope to eventually fully automate the process of repairing programs. A key challenges is ambiguity, as multiple codes -- or fixes -- can implement the same functionality. In addition, dataset by nature fail to capture the variance introduced by such ambiguities. Therefore, we propose a deep generative model to automatically correct programming errors by learning a distribution of potential fixes. Our model is formulated as a deep conditional variational autoencoder that samples diverse fixes for the given erroneous programs. In order to account for ambiguity and inherent lack of representative datasets, we propose a novel regularizer to encourage the model to generate diverse fixes. Our evaluations on common programming errors show for the first time the generation of diverse fixes and strong improvements over the state-of-the-art approaches by fixing up to $61\%$ of the mistakes.

Accurate expected time of arrival (ETA) information is crucial in maintaining the quality of service of public transit. Recent advances in artificial intelligence (AI) has led to more effective models for ETA estimation that rely heavily on a large GPS datasets. More importantly, these are mainly cabs based datasets which may not be fit for bus-based public transport. Consequently, the latest methods may not be applicable for ETA estimation in cities with the absence of large training data set. On the other hand, the ETA estimation problem in many cities needs to be solved in the absence of big datasets that also contains outliers, anomalies and may be incomplete. This work presents a simple but robust model for ETA estimation for a bus route that only relies on the historical data of the particular route. We propose a system that generates ETA information for a trip and updates it as the trip progresses based on the real-time information. We train a deep learning based generative model that learns the probability distribution of ETA data across trips and conditional on the current trip information updates the ETA information on the go. Our plug and play model not only captures the non-linearity of the task well but that any transit agency can use without needing any other external data source. The experiments run over three routes, data collected in the city of Delhi illustrates the promise of our approach.

This survey presents the most relevant neural network models of autism spectrum disorder and schizophrenia, from the first connectionist models to recent deep network architectures. We analyzed and compared the most representative symptoms with its neural model counterpart, detailing the alteration introduced in the network that generates each of the symptoms, and identifying their strengths and weaknesses. For completeness we additionally cross-compared Bayesian and free-energy approaches. Models of schizophrenia mainly focused on hallucinations and delusional thoughts using neural disconnections or inhibitory imbalance as the predominating alteration. Models of autism rather focused on perceptual difficulties, mainly excessive attention to environment details, implemented as excessive inhibitory connections or increased sensory precision. We found an excessive tight view of the psychopathologies around one specific and simplified effect, usually constrained to the technical idiosyncrasy of the network used. Recent theories and evidence on sensorimotor integration and body perception combined with modern neural network architectures offer a broader and novel spectrum to approach these psychopathologies, outlining the future research on neural networks computational psychiatry, a powerful asset for understanding the inner processes of the human brain.

Recently, click-through rate (CTR) prediction models have evolved from shallow methods to deep neural networks. Most deep CTR models follow an Embedding\&MLP paradigm, that is, first mapping discrete id features, e.g. user visited items, into low dimensional vectors with an embedding module, then learn a multi-layer perception (MLP) to fit the target. In this way, embedding module performs as the representative learning and plays a key role in the model performance. However, in many real-world applications, deep CTR model often suffers from poor generalization performance, which is mostly due to the learning of embedding parameters. In this paper, we model user behavior using an interest delay model, study carefully the embedding mechanism, and obtain two important results: (i) We theoretically prove that small aggregation radius of embedding vectors of items which belongs to a same user interest domain will result in good generalization performance of deep CTR model. (ii) Following our theoretical analysis, we design a new embedding structure named res-embedding. In res-embedding module, embedding vector of each item is the sum of two components: (i) a central embedding vector calculated from an item-based interest graph (ii) a residual embedding vector with its scale to be relatively small. Empirical evaluation on several public datasets demonstrates the effectiveness of the proposed res-embedding structure, which brings significant improvement on the model performance.

This paper presents a computational model for conceptual shifts, based on a novelty metric applied to a vector representation generated through deep learning. This model is integrated into a co-creative design system, which enables a partnership between an AI agent and a human designer interacting through a sketching canvas. The AI agent responds to the human designer's sketch with a new sketch that is a conceptual shift: intentionally varying the visual and conceptual similarity with increasingly more novelty. The paper presents the results of a user study showing that increasing novelty in the AI contribution is associated with higher creative outcomes, whereas low novelty leads to less creative outcomes.

Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule, which limits their applicability for reactive chemistry and chemical analysis. Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for target electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry.

Probabilistic optimal power flow (POPF) is an important analytical tool to ensure the secure and economic operation of power systems. POPF needs to solve enormous nonlinear and nonconvex optimization problems. The huge computational burden has become the major bottleneck for the practical application. This paper presents a deep learning approach to solve the POPF problem efficiently and accurately. Taking advantage of the deep structure and reconstructive strategy of stacked denoising auto encoders (SDAE), a SDAE-based optimal power flow (OPF) is developed to extract the high-level nonlinear correlations between the system operating condition and the OPF solution. A training process is designed to learn the feature of POPF. The trained SDAE network can be utilized to conveniently calculate the OPF solution of random samples generated by Monte-Carlo simulation (MCS) without the need of optimization. A modified IEEE 118-bus power system is simulated to demonstrate the effectiveness of the proposed method.